System and methods for generating predictive combinations of hospital monitor alarms

Abstract

Systems and methods are disclosed for monitoring data associated with a plurality of physiological characteristics of a patient, comprising: the methods include generating a set of super-alarm patterns associated with the plurality of physiological conditions, wherein the super-alarm patterns comprising data relating to a combination of at least two individual raw alarms from independent physiological data streams that co-occur within a temporal window, and triggering an alarm if a combination of the input physiological data matches at least a portion of a generated super-alarm pattern.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application is a 35 U.S.C. §111(a) continuation of PCT international application number PCT / US2012 / 060135 filed on Oct. 12, 2012, incorporated herein by reference in its entirety, which claims priority to, and the benefit of, U.S. provisional patent application Ser. No. 61 / 547,022 filed on Oct. 13, 2011, incorporated herein by reference in its entirety. Priority is claimed to each of the foregoing applications.[0002]The above-referenced PCT international application was published as PCT International Publication No. WO 2013 / 056180 on Apr. 18, 2013, incorporated herein by reference in its entirety.STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT[0003]Not ApplicableINCORPORATION-BY-REFERENCE OF MATERIAL SUBMITTED IN A COMPUTER PROGRAM APPENDIX[0004]Not ApplicableNOTICE OF MATERIAL SUBJECT TO COPYRIGHT PROTECTION[0005]A portion of the material in this patent document is subject to copyright protection under the copyright ...

AI Technical Summary

Benefits of technology

The present invention is a method for analyzing monitor alarms to predict adverse events, such as code blue arrests in hospitals. The method uses itemset mining and information metric based discretization to extract patterns from the alarm combinations that are predictive of code blue events. The technical effects of this invention include improved prediction and prevention of adverse events, improved safety in hospitals, and reduced risk of legal liability.

Problems solved by technology

However, they are often criticized for generating an excessive number of false positive and false alarms.

Frequent false positive alarms not only create annoying distractions but also can cause alarm fatigue for bedside care givers so that attentions to critical alarms are missed raising serious patient safety concerns.

Indeed, recent mainstream reports have published cases of avoidable patient deaths that were unfortunately related to the alarm fatigue / desensitization among bedside care givers.

False positive alarms can be caused either by false alarms due to noise and artifacts in signals or by inappropriate alarming criteria that are too generic and sensitive.

Indeed, most of the threshold-based alarms despite being true alarms are false positives.

Reducing the false positive rate beyond reducing the number of false alarms is more challenging because of the need for highly sensitive monitoring in an acute care setting.

Images